Agentic AI Engineer (Xora Portfolio Company)
HybridSingapore, Singapore or San Diego, California, United States
Job Summary
Design provider abstractions for multi-model workflows with structured validation, retries, and cost tracking. Build agent orchestration loops that dispatch sub-agents in parallel with durable checkpoints and stateful memory management. Implement human-in-the-loop checkpoints for low-confidence steps and wrap platform capabilities as typed, registered tools. Engineer end-to-end retrieval systems including ingestion, embeddings, chunking, and hybrid search to ground model calls. Version prompts and capture reasoning traces to ensure inspectability, while instrumenting every invocation with lineage spans for debugging. Construct deterministic evaluation frameworks using LLM-as-judge scoring to gate regressions. Manage agent access behind a single integration point consumed by backend services, frontend, and notebooks.
Required Qualifications
- Bachelor's or Master's degree in Computer Science or a related engineering field
- 5+ years building and shipping production software
- real depth building LLM or agent systems in production
- Strong Python
- solid engineering practice: async code, typing, testing, modular design, and code review
- a track record of shipping systems others depend on
- Hands-on experience building agentic or LLM systems in production
- orchestration loops
- tool-calling
- structured outputs
- context and memory management for reliable long-running workflows
- Experience working across multiple model providers behind a single abstraction
- routing
- fallback
- a feel for the cost and latency trade-offs
- Experience building retrieval systems end to end
- embeddings
- chunking
- hybrid search
- reranking
- vector databases
- Experience with LLM evaluation and guardrails
- building eval sets and harnesses
- LLM-as-judge scoring
- regression gating
- output-quality and safety checks
- Experience instrumenting LLM systems for observability
- tracing model and tool calls
- versioning prompts
- using traces to debug and improve real behavior
- Comfort owning ambiguous systems end to end in a fast-moving early-stage environment
- Singapore or United States
- Work model is on-site or hybrid, set per location
Desired Qualifications
- Stateful agent-orchestration frameworks such as LangGraph or AutoGen
- durable-execution engines such as Temporal for long-running workflows
- Experience building MCP tools or servers, or similar tool-calling integration layers
- LLMOps and evaluation tooling such as MLflow or Langfuse for tracing, prompt versioning, and evaluation
- Human-in-the-loop and interrupt-driven agent patterns for review and control
- Applying LLMs to scientific or technical workflows
- grounding reasoning in tool outputs and structured data
- Fluency with modern AI coding assistants
- open-source contributions to AI or agent tooling
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.